Smart factory companies are installing various sensors in production facilities and collecting field data. However, there are relatively few companies that actively utilize collected data, academic research using field data is actively underway. This study seeks to develop a model that detects anomalies in the process by analyzing spindle power data from a company that processes shafts used in automobile throttle valves. Since the data collected during machining processing is time series data, the model was developed through unsupervised learning by applying the Holt Winters technique and various deep learning algorithms such as RNN, LSTM, GRU, BiRNN, BiLSTM, and BiGRU. To evaluate each model, the difference between predicted and actual values was compared using MSE and RMSE. The BiLSTM model showed the optimal results based on RMSE. In order to diagnose abnormalities in the developed model, the critical point was set using statistical techniques in consultation with experts in the field and verified. By collecting and preprocessing real-world data and developing a model, this study serves as a case study of utilizing time-series data in small and medium-sized enterprises.

Injection molding is a process of shaping resin materials by heating them to a temperature above their melting point and then using a mold. The resin material is injected into and cooled within the mold cavity, solidifying into the desired shape. The core and cavity components that make up the mold cavity are crucial elements for the precision molding in injection molding. In the case of precision mold production, the application of 5-axis machining technology is required to ensure high machining quality for complex shapes, and among these factors, the tool angle is a critical machining condition that determines the surface roughness of the workpiece. In this study, we aim to measure the surface roughness of the machined surface of KP4A specimens during machining processes with variations in the tool angle and analyze the correlation between the tool angle and surface roughness.

Recently, halogen lamps for vehicle exterior lamp systems are being replaced by LEDs (Light Emitting Diode) in consideration of miniaturization, power consumption, life, luminance, and eco-friendliness. Due to regulations on the amount of light required, luminance, light uniformity, and glare prevention, it is required to develop a light guide for controlling a light source of an LED lamp for a vehicle. For the development of the light guides, the development of machining technology that can cut micro patterns of hundreds of micrometers scale into surface roughness of tens of nanometers scale must be preceded. In this study, the effect of variations in cutting conditions on surface roughness was analyzed through experiments. The micro patterns was manufactured by cutting into STAVAX material, and the surface of the micro patterns was super-finished using a ball-shaped PCD (polycrystalline diamond) tool without flutes. In experiments, the cutting conditions of the super-finishing process were varied, and the varied cutting conditions were feed rate, radial depth of cut, and spindle speed

The function of coolant in machining is to reduce the frictional force in the contact area in between the tool and the material, and to increase the precision by cooling the work-piece and the tool, to make the machining surface uniform, and to extend the tool life. However, cutting oil is harmful to the human body because it uses chlorine-based extreme pressure additives to cause environmental pollutants. In this study, the effect of cutting temperature and surface roughness of titanium alloy for medical purpose (Ti-6Al-7Nb) in eco-friendly ADL slot shape machining was investigated using the response surface analysis method. As the design of the experiment, three levels of cutting speed, feed rate, and depth of cut were designed and the experiment was conducted using the central composite planning method. The regression expressions of cutting temperature and surface roughness were respectively obtained as quadratic functions to obtain the minimum value and optimal cutting conditions. The values from this formula and the experimental values were compared. As a result, this study makes and establishes the basis to prevent environmental pollution caused by the use of coolant and to replace it with ADL (Aerosol Dry Lubricant) machining that uses a very small amount of vegetable oil with high pressure.

Recently, it is being carried out the project to evaluate the properties of materials harvested from nuclear reactor after the decommissioning of Kori Unit 1. However, it is not sufficient adequate machining equipment and remote machining technique to perform the projects for evaluation of materials harvested from nuclear reactor. Thus, it is required to develop the remote machining technique in hotcell to evaluate the mechanical properties of nuclear reactor materials. The machining technique should be performed inside a hotcell to evaluate mechanical properties of materials harvested from nuclear reactor and is essential to prevent radiation exposure of workers. Also, it is essential to design the apparatus and develop the machining process so that it can be operated with a manipulator and minimize contamination in hotcell. In this research, development of remote specimen machining technique in hotcell such as machining apparatus, technique and process for compact tension specimens of material harvested from nuclear reactor are described. Remote machining technique will be useful in specimen machining to evaluate changes in mechanical properties of materials harvested in high-radioactive reactor. Also, it is expected that various types of specimens can be machining by applying the developed machining technique in the future.

The purpose of using coolant in machining is both to increase a tool life and also to prevent product deformation and thus, stabilize the surface quality by lubricating and cooling the tool and the machining surface. However, a very small amount of cutting mist should be used because chlorine-based extreme pressure additives are used to generate environmental pollutants in the production process and cause occupational diseases of workers. In this study, medical titanium alloy (Ti-6Al-7Nb) was subjected to a processing experiment by selecting factors and levels affecting cutting power in the processing of the Aerosol Dry Lubrication (ADL) method using vegetable oil. The machining shape was a slot to sufficiently reflect the effect of the cutting depth. As for the measurement of cutting force, the trend of cutting characteristics was identified through complete factor analysis. The factors affecting the cutting force of ADL slot processing were identified using the reaction surface analysis method, and the characteristics of the cutting force according to the change in factor level were analyzed. As the cutting speed increased, the cutting force decreased and then increased again. The cutting force continued to increase as the feed speed increased. The increase in the cutting depth increased the cutting force more significantly than the increase in the cutting speed and the feed speed. Through the reaction surface analysis method, the regression equation for predicting cutting force was identified, and the optimal processing conditions were proposed. The cutting force was predicted from the secondary regression equation and compared with the experimental value.

In this present investigation, machinability studies on novel aluminum composite with hybrid reinforcements of copper-coated 4% carbon fibers (CFs) and 3% nanoclay in AA6026 matrix fabricated by compocasting method is performed. Step drill bit and multifaceted drill bit are used by adopting central composite design (CCD) in response surface methodology (RSM). The outcomes show that, with a rise in rotational speed surface irregularities, resultant force and material removal rate (MRR) intensifies, and with the additional rise in rotational speed, all the outputs decrease considerably. High MRR, resultant cutting force, and surface roughness are obtained with multifaceted carbide drills, compared with a step drill. Desirability function is used to maximize the MRR and minimize the resultant cutting forces considering the constant surface roughness of 3 μm. The optimal values are rotational speed of 1285 rpm, feed rate of 60 mm/min with the step drill bit, producing an MRR of 0.0439 kg/sec and a resultant cutting force of 185.818 N. The second-order empirical models are developed for outputs, which are fed into the non-traditional metaheuristic Evaporation Rate-based Water Cycle Algorithm (ER-WCA) therefore the lower objective value is achieved with step drill of 51.7421. It is found that using a step drill the machinability performance of this hybrid nanocomposite is well improved than the machining with other drill bits. This composite fulfills the norms of 2000/53/CE-ELV European environmental directives.

Many countries are developing various mechanical cutting technologies to dismantle nuclear facility. However, most of mechanical cutting technologies have a problem like the degradation of tool life due to the Hard-Machining materials. To solve this problem, lab-scale test was performed with a Plasma Assisted Machining (PAM) technology and 25 mm of thickness Inconel 600 plate. Commonly, the strength of metals decreases by exposure at high temperature. And, previous study reported that strength of Inconel 600 is degraded above 500°C. This softening effect was applied to Inconel 600 cutting test. The optimal conditions such as the plasma torch power and the feed rate were determined by this study. As a result, the surface temperature of Inconel 600 was reached up to 500°C under the conditions which is 8.4 kW of plasma torch power and 150–250 mm·min−1 of feed rate. And it was confirmed that the tool life was improved under the conditions. In order to apply PAM for various Hard- Machining materials, it is necessary to investigate the softening temperature of Hard-Machining materials, the plasma torch power and feed rate.

Carbon fiber and its composites are increasingly used in many fields including defence, military, and allied industries. Also, surface quality is given due importance, as mating parts are used in machineries for their functioning. In this work, the turning process is considered for Carbon Fiber Reinforced Polymer (CFRP) composites by varying three important cutting variables: cutting speed, feed, and depth of cut. Correspondingly, the surface roughness is measured after the completion of turning operation. As well, a prediction model is created using different fuzzy logic membership function and Levenberg–Marquardt algorithm (LMA) in artificial intelligence. Later, the surface roughness values from the developed models are compared against the experimental values for its correlation and effectiveness in using different membership functions of fuzzy logic and ANN. Thus, the experimental results are analyzed using the effect graphs and it is presented in detail.

This article suggests the machine learning model, i.e., classifier, for predicting the production quality of free-machining 303-series stainless steel(STS303) small rolling wire rods according to the operating condition of the manufacturing process. For the development of the classifier, manufacturing data for 37 operating variables were collected from the manufacturing execution system(MES) of Company S, and the 12 types of derived variables were generated based on literature review and interviews with field experts. This research was performed with data preprocessing, exploratory data analysis, feature selection, machine learning modeling, and the evaluation of alternative models. In the preprocessing stage, missing values and outliers are removed, and oversampling using SMOTE(Synthetic oversampling technique) to resolve data imbalance. Features are selected by variable importance of LASSO(Least absolute shrinkage and selection operator) regression, extreme gradient boosting(XGBoost), and random forest models. Finally, logistic regression, support vector machine(SVM), random forest, and XGBoost are developed as a classifier to predict the adequate or defective products with new operating conditions. The optimal hyper-parameters for each model are investigated by the grid search and random search methods based on k-fold cross-validation. As a result of the experiment, XGBoost showed relatively high predictive performance compared to other models with an accuracy of 0.9929, specificity of 0.9372, F1-score of 0.9963, and logarithmic loss of 0.0209. The classifier developed in this study is expected to improve productivity by enabling effective management of the manufacturing process for the STS303 small rolling wire rods.

Recently, with the development of ultra-precision technology, the quality improvement of optical parts and various products is emerging. The need for a difficult-to-cut material that is light and exhibits high hardness and high strength physical properties is being emphasized. Ultra-precision machining processing solutions for these difficult-to-cut materials are being actively developed. In this research, experiments were performed using a DTM machine equipped with a laser-assisted machining module for ultra-precision machining of CaF2 materials that are brittle but exhibit high transmittance in a wide range from ultraviolet to infrared.

This study suggests a machine learning model for predicting the production quality of free-machining 303-series stainless steel small rolling wire rods according to the manufacturing process's operation condition. The operation condition involves 37 features such as sulfur, manganese, carbon content, rolling time, and rolling temperature. The study procedure includes data preprocessing (integration and refinement), exploratory data analysis, feature selection, machine learning modeling. In the preprocessing stage, missing values and outlier are removed, and variables for the interaction between processes and quality influencing factors identified in existing studies are added. Features are selected by variable importance index of lasso regression, extreme gradient boosting (XGBoost), and random forest models. Finally, logistic regression, support vector machine, random forest, and XGBoost is developed as a classifier to predict good or defective products with new operating condition. The hyper-parameters for each model are optimized using k-fold cross validation. As a result of the experiment, XGBoost showed relatively high predictive performance compared to other models with accuracy of 0.9929, specificity of 0.9372, F1-score of 0.9963 and logarithmic loss of 0.0209. In this study, the quality prediction model is expected to be able to efficiently perform quality management by predicting the production quality of small rolling wire rods in advance.

When the product is taken out after the injection process, the surface of the product and the mold are attached and to separate them, it is necessary to consider the frictional force between the mold surface and the product surface. Therefore, to reduce the frictional force, a subtraction gradient for the rib shape is generally applied, and a lapping process is performed to improve the surface roughness of the rib shape surface of the processed mold. Therefore, research is needed to improve the surface roughness when processing the rib. In this study, slotting processing was applied to improve surface roughness when processing ribs. Slotting processing is a processing method that removes material through the feed motion of the tool, and processing is possible regardless of the aspect ratio of the processing shape. A slotting tool was developed for rib machining and a comparative experiment with electric discharge machining was performed. Also after processing, the surface roughness and processing time were compared and analyzed, and the improved surface roughness and fast processing time characteristics of the slotting processing compared to electric discharge processing were confirmed.